Skip to content
ModelCap

Nemotron Cascade 2 30B A3B

Current board #108Official publisher releaseRestricted license7d #175 → #108

NVIDIA·nvidia/Nemotron-Cascade-2-30B-A3B

Nemotron Cascade 2 30B A3B is ModelCap current-board rank #108 with Index 38.4 (Modeled · prior), from the ModelCap Index as of 9 Sept 2026, 20:46 UTC.

Nemotron Cascade 2 30B A3B weight access is restricted license, from ModelCap classification of published repository metadata as of 9 Sept 2026, 20:46 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
38.4#108
Estimated · 40% support · score interval 16.9–60.0
No admitted evaluation publication timestamp yet
Market Gravity
10.1
Secondary market signal

OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.

Input
Unlisted
no listed API price
Output
Unlisted
no listed API price
Context
tokens
Providers
0
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

Reported evaluation leads (1)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. Rows marked as used were laddered against independently measured peers inside the launch-card channel of this model's modeled placement, with the replay-measured optimism haircut applied; the others played no part.

Dataset / taskMetricValueRevisionProvenance
Idavidrein/gpqa
diamond
76.1
Unpinned
not published
Reported
Not used in launch estimate

ModelCap Index · Current board

Methodology
38.4
Modeled · prior · calibrated architecture-and-release-era fallback from static public metadata
Current board
#108
Public rank basis
Modeled · prior (architecture)
Index support
40.0% · limited
Index interval
16.9–60.0
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
No admitted evaluation publication timestamp
Identity binding
Exact catalogue product · nvidia/nvidia/Nemotron-Cascade-2-30B-A3B · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata nvidia/Nemotron-Cascade-2-30B-A3B@6327cdbcf907e1c7cec9cb29fb6e6cebdf8feaf7 (not the evaluation revision)
Index observations used
0
Qualified Index evidence point
38.4
How this position was produced · fused launch placement

No general-family board lists this model yet. Its point estimate is the precision-weighted mean of every channel that spoke for it; each channel’s share is the weight it carried. Independent measurements replace this placement as boards list the model.

Fused estimate
38.4 ± 16.9
Independent share
0%
Shrink toward corpus
+4.9
Peer ceiling share
27%
Optimism haircut
None required · cross lab probe, 12 probes
Method
precision-weighted-v1
Channels fused into this model’s launch placement
ChannelEstimateShare
Publisher corpus prior · not independent
publisher-corpus-prior over 182 held-out anchors
42.1 ± 22.357%
Launch card against resolved peers · not independent
launch card against 3 resolved peers on 11 rows
33.6 ± 25.743%
  • · Launch card row aa-lcr: inside the resolved peer range
  • · Launch card row bfcl-v-4: claims below every resolved peer
  • · Launch card row gpqa-diamond: inside the resolved peer range
  • · Launch card row hle: inside the resolved peer range
  • · Launch card row hmmt-feb-25: claims above every resolved peer
  • · Launch card row ifbench: claims above every resolved peer
  • · Launch card row imo-answerbench: claims above every resolved peer
  • · Launch card row mmlu-pro: inside the resolved peer range
  • · Launch card row mmlu-prox: inside the resolved peer range
  • · Launch card row scicode: inside the resolved peer range
  • · Launch card row terminal-bench-2-0: inside the resolved peer range
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
Evidence status
No admitted measured evidence
General preference
Coding
Agents & tools
Reasoning
Evidence breadth
0%
Evidence coverage
0%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
Liquidity (providers × uptime)
Open reach (HF downloads)
Surface (context / tools / modalities)
0.0
Freshness
51.4
  • · Catalogue surface
  • · First seen 2026-03-18

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Experimental capability estimate

Estimate policy
38.2
18.6–57.7 uncertainty interval
Excluded from rank
Confidence
68%
Training support
187 models · 107 lineages
Out-of-domain check
in domain
Feature coverage
71%
Lineage-held-out error
10.4 MAE

Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.

Deployment readiness

Metadata index
46.4
partial · 52% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
92.5
Deployability
8.0
Evaluation provenance
0.0

Missing: artifactReproducibility.base-lineage, deployability.independent-provider-records, deployability.measured-provider-uptime, deployability.published-provider-pricing, deployability.declared-capacity, evaluationProvenance.admitted-evaluation-observations, evaluationProvenance.capability-family-breadth, evaluationProvenance.evaluation-source-diversity, evaluationProvenance.identity-and-source-confidence, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
10.1
OpenRouter weekly popularity
Not listed

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

No matched Arena rating

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%
0.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
51.4

Time since first public availability, on a six-month half-life.

Specification

Context window
tokens
Max output
Inputs
Text
Outputs
Text
Tokenizer
Cached input tokens
Not offered
First seen on OpenRouter
18 Mar 2026

Capabilities

  • Not supported: Reasoning
  • Not supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Not supported: Moderated

Weights & access

Restricted license. Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment.

Access
Restricted license
Pinned revision
6327cdbcf907
Parameters
31.6B
Architecture
NemotronHForCausalLM
Model type
nemotron_h
Hugging Face downloads (30d)
Downloads (all time)
Likes
Repository updated
9 Jul 2026, 22:10 UTC

Metadata status: stale · HTTP 429.

Compare Nemotron Cascade 2 30B A3B with

Pick any model

Benchmark leaderboards featuring Nemotron Cascade 2 30B A3B

All leaderboards
Public benchmark boards on which Nemotron Cascade 2 30B A3B has a published result
LeaderboardScoreSource rankConfigurationPublished
Terminal-Bench 2.1 (Artificial Analysis run)Artificial Analysis20.6%#174 of 236terminal-bench:2.1:terminus-2:e2b:pass-at-1:3-repeats:source-model="Nemotron Cascade 2 30B A3B":reasoning=true9 Sept 2026
τ²-Bench Telecom (Artificial Analysis run)Artificial Analysis53.2%#199 of 436tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Nemotron Cascade 2 30B A3B":reasoning=true9 Sept 2026
Humanity's Last Exam (Artificial Analysis run)Artificial Analysis12.0%#241 of 603hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Nemotron Cascade 2 30B A3B":reasoning=true9 Sept 2026

Alternatives to Nemotron Cascade 2 30B A3B, by the numbers

Ranked neighbours

Models within 3 places of #108 on the ModelCap Index.

Other ranked NVIDIA models

The same publisher's other current models with a public Index position.

Nemotron Cascade 2 30B A3B: common questions

How does Nemotron Cascade 2 30B A3B rank among AI models?

Nemotron Cascade 2 30B A3B holds ModelCap Index position #108 of 160 ranked language models as of 9 September 2026, with an Index score of 38.4 (interval 16.9–60.0); evidence: modeled · prior. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does Nemotron Cascade 2 30B A3B cost per 1M tokens?

No live API price is listed for Nemotron Cascade 2 30B A3B in the current snapshot as of 9 September 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.

Is Nemotron Cascade 2 30B A3B open-weight?

Restricted license (nvidia-open-model-license). Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment. The repository is nvidia/Nemotron-Cascade-2-30B-A3B on Hugging Face.

Which benchmarks has Nemotron Cascade 2 30B A3B been evaluated on?

Nemotron Cascade 2 30B A3B has published results on 3 public boards tracked by ModelCap as of 9 September 2026: AA Terminal-Bench 2.1 20.6% (#174 of 236), AA τ²-Bench Telecom 53.2% (#199 of 436) and AA Humanity's Last Exam 12.0% (#241 of 603). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

How does Nemotron Cascade 2 30B A3B compare with Nemotron 3 Super?

Nemotron Cascade 2 30B A3B ranks #108 (Index 38.4) and Nemotron 3 Super ranks #107 (Index 38.9) on the ModelCap Index as of 9 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was Nemotron Cascade 2 30B A3B released?

Nemotron Cascade 2 30B A3B first appeared in the catalogue on 18 Mar 2026. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.